CN111814614A - Intelligent object-identifying electronic scale weighing method and system - Google Patents
Intelligent object-identifying electronic scale weighing method and system Download PDFInfo
- Publication number
- CN111814614A CN111814614A CN202010593753.3A CN202010593753A CN111814614A CN 111814614 A CN111814614 A CN 111814614A CN 202010593753 A CN202010593753 A CN 202010593753A CN 111814614 A CN111814614 A CN 111814614A
- Authority
- CN
- China
- Prior art keywords
- model
- commodity
- data set
- picture
- training
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/20—Scenes; Scene-specific elements in augmented reality scenes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01G—WEIGHING
- G01G19/00—Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups
- G01G19/40—Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups with provisions for indicating, recording, or computing price or other quantities dependent on the weight
- G01G19/413—Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups with provisions for indicating, recording, or computing price or other quantities dependent on the weight using electromechanical or electronic computing means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24133—Distances to prototypes
- G06F18/24137—Distances to cluster centroïds
- G06F18/2414—Smoothing the distance, e.g. radial basis function networks [RBFN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Biology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a weighing method and a system of an intelligent object-identifying electronic scale, which comprises the following specific implementation steps: 1) collecting pictures of common commodities in a supermarket and preprocessing the pictures; 2) manually marking the category of each commodity picture and making the category into a training data set; 3) constructing a deep convolutional neural network based on increment-v 4; 4) training the model by using a training data set, and storing the trained commodity identification model; 5) acquiring a commodity picture on terminal equipment; 6) inputting the picture into a commodity identification model; 7) the commodity identification model returns to a commodity label printing position; the invention classifies the pictures, then performs terminal image recognition, obtains unit prices from the recognized articles, performs pricing by combining with weight data, and can complete the electronic weighing process without depending on operators, thereby realizing a weighing self-service shopping mode, having simple and convenient shopping process and high intelligent degree and effectively reducing labor cost.
Description
Technical Field
The invention belongs to the technical field of electronic operation, and particularly relates to a weighing method and a weighing system of an intelligent object-identifying electronic scale.
Background
The conventional electronic scale is widely applied to weighing and pricing of articles in places such as supermarkets, markets and the like, and has the advantages of convenience and quickness compared with the conventional manual weighing and pricing; but present electronic scale still need rely on operating personnel just can accomplish article and weigh, valuation and print bar code, and the realization process is comparatively loaded down with trivial details and required cost of labor is high, and its main flow lies in: in each weighing process, firstly, an operator is required to manually select weighed commodities, and the process is very complicated because of a large number of categories of the large supermarket; although many supermarkets now allow purchasers to weigh themselves in order to reduce queuing, the purchasers are not familiar with the product types or cannot distinguish the same type of products, and the weighing process is much more time-consuming than the operation of a supermarket weighing specialist; as the types of items being traded, the number of times they are weighed, increase further complicating the trading process and increasing the workload of the playground personnel.
Disclosure of Invention
The invention aims to solve the problems in the background art, and provides an intelligent object-identifying electronic scale weighing method and system.
In order to achieve the purpose, the weighing method of the intelligent object-identifying electronic scale comprises the following specific implementation steps:
1) collecting pictures of common commodities in a supermarket and preprocessing the pictures;
2) manually marking the category of each commodity picture and making the category into a training data set;
3) constructing a deep convolutional neural network based on increment-v 4;
4) training the model by using a training data set, and storing the trained commodity identification model;
5) acquiring a commodity picture on terminal equipment;
6) inputting the picture into a commodity identification model;
7) the commodity identification model returns to the commodity label printing place.
Further, in step 1), the image preprocessing mainly includes cutting the image to a uniform size, performing processing related to color acquisition, shape acquisition, mark acquisition and contrast acquisition on the image, ignoring an excessively dark portion, and accelerating the operation speed.
Further, in step 2), the training data set is divided into two parts, according to 8: 2, the data set is divided into a training data set and a testing data set, the training data set is used for training the model, and the testing data set is used for testing the effect of the model and adjusting the optimization method and parameters to prevent the overfitting phenomenon.
Further, in step 3), when the neural network model is constructed, the output category number of the model, namely the category number of the commodity, needs to be selected; the loss function value represents the difference between the predicted picture result and the real result, and the lower the loss function value is, the closer the loss function value is to the real result; when a model is constructed, more optimal training parameters including cycle times, learning rate and picture amount of each training need to be selected according to different loss function value results; when the loss function oscillates near the lowest value and does not stably descend any more, the model is shown to be trained to be ended, and the training process is ended in advance to avoid overfitting; the Incep-v 4 adopts an asynchronous SGD (random gradient descent) method, and the learning rate is reduced by 4% for 8 iterations; the final model will evaluate the model performance based on top-1 and top-5 error rates on the test data set.
Further, in step 4), parameters are selected to determine that a new model is trained when the model is trained, and new commodities are added on the basis of the original model; the commodity pictures collected on the terminal equipment also need to be subjected to image preprocessing; in the identification process, the picture is transmitted into a trained commodity identification model, the model extracts a characteristic matrix from the picture through a series of parameters, and the commodity category with the maximum probability corresponding to the characteristic matrix is returned.
Further, in step 6), acquiring unit prices corresponding to the identified articles by querying a pre-established transaction article unit price database; the trading item unit price database is composed of each trading item and corresponding unit price, and after the item to be traded is identified, the corresponding unit price can be obtained by inquiring the trading item unit price database without manual input of an operator. And when the transaction article is updated, correspondingly updating the transaction article unit price database and the image identification template.
The invention also discloses a weighing system of the intelligent object-identifying electronic scale, which comprises a microprocessor for background processing, and a pressure sensor, a camera and a sound device which are respectively connected with the microprocessor;
the pressure sensor is used for acquiring weight data of an article to be traded, and the weight data is amplified and subjected to AD conversion and then transmitted to the microprocessor through a serial port of the single chip microcomputer;
the camera is used for acquiring image data of an article to be traded;
the micro processor is used for receiving data input by the pressure sensor and the camera to carry out intelligent pricing, receiving weight data output by the pressure sensor and image data acquired by the camera by the micro processor to carry out image recognition, calculating the total price of the article to be traded according to the XML unit price database after recognizing the category of the article to be traded, and outputting settlement data through sound equipment after voice synthesis.
And further, the system also comprises an administrator interface, wherein the administrator interface displays the initialization setting information, the transaction article updating information and the transaction article option information, and controls printing to perform corresponding operation after voice recognition.
The invention has the advantages that:
the intelligent object-identifying electronic scale weighing method and system provided by the invention have the advantages that the characteristic matrix on the picture is extracted, the loss function and the back propagation algorithm are utilized, the picture is classified according to different characteristics, then the terminal image recognition is carried out, the unit price is obtained by the recognized object, the pricing is carried out by combining the weight data, the electronic weighing process can be completed without depending on an operator, so that the weighing self-service shopping mode is realized, the shopping process is simple and convenient, the intelligent degree is high, and the labor cost can be effectively reduced.
Drawings
FIG. 1 is a schematic diagram of a weighing system of an intelligent electronic scale for identifying a subject according to the present invention;
FIG. 2 is a flow chart of a neural network model constructed in the weighing method of the intelligent electronic scale for identifying a subject.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments.
As shown in fig. 1-2, the present invention is a structural schematic diagram of a weighing method and a system of an intelligent electronic scale for identifying a subject, and the weighing method of the present invention comprises the following specific steps:
1) the method comprises the steps of collecting common commodity pictures in a supermarket and preprocessing the pictures, wherein the pictures are collected by photographing commodities in a fruit area or a vegetable area, then the collected pictures are preprocessed, the picture preprocessing mainly comprises the steps of cutting the pictures to be uniform in size, carrying out color collection, shape collection, mark collection and contrast-related processing on the pictures, ignoring too dark parts, and accelerating the operation speed.
2) Manually marking the category of each commodity picture and making the commodity picture into a training data set, wherein the training data set is divided into two parts according to the following steps of 8: 2 into a training data set for training the model and a test data set for testing the model effect and adjusting the optimization method and parameters to prevent the over-fitting phenomenon.
3) Constructing a deep convolution neural network based on increment-v 4, wherein when a neural network model is constructed, the output class number of the model, namely the class number of a commodity, needs to be selected; the loss function value represents the difference between the predicted picture result and the real result, and the lower the loss function value is, the closer the loss function value is to the real result; when a model is constructed, more optimal training parameters including cycle times, learning rate and picture amount of each training need to be selected according to different loss function value results; when the loss function oscillates near the lowest value and does not stably descend any more, the model is shown to be trained to be ended, and the training process is ended in advance to avoid overfitting; the Incep-v 4 adopts an asynchronous SGD (random gradient descent) method, and the learning rate is reduced by 4% for 8 iterations; finally, the model evaluates the performance of the model according to the top-1 and top-5 error rates on a test data set, for fruits with larger differences, bananas, apples, Hami melons, watermelons, pears, dragon fruits and grapes are set into separate categories, the models are constructed for the fruits with different varieties and prices in the same category, the difference between the predicted picture result and the real result is reflected by loss function values, the lower the loss function values are, the closer the real result is represented, taking four different varieties of apples as an example, wherein green apples, common apples, red Fuji apples and high-quality apples, the shapes of the apples in 4 are close, the colors of the green apples and the other three apples are different, the green apples and the other three apples are distinguished by the color loss function values, and the color difference boundary of the common apples, the red Fuji apples and the high-quality apples is fuzzy, wherein the common apple has a certain difference with the red Fuji apple and the high-quality apple, the common apple has poor apple spot, the red part and the cyan part of the same apple and the sunny side and the shady side of the same apple have higher contrast, the common apple can be distinguished from the red Fuji apple and the high-quality apple by the contrast loss function value, the red Fuji apple and the high-quality apple are different, the shapes of the red Fuji apple and the high-quality apple are larger and smaller, the distinguishing by the shape loss function value is difficult, the apple spot and the color are closer, in order to distinguish the red Fuji apple and the high-quality apple, a net bag or a label is sleeved on the red Fuji apple or the high-quality apple, the distinguishing by the net bag or the label is adopted, the difference between the red Fuji apple and the high-quality apple is distinguished by the label loss function value, under the condition that the varieties of the apples are further increased, the model is further built by different markings or different color markings.
4) Training a model by using a training data set, storing a trained commodity identification model, determining to be a new training model by selecting parameters during model training, and adding new commodities on the basis of an original model; the commodity pictures collected on the terminal equipment also need to be subjected to image preprocessing; in the identification process, the picture is transmitted into a trained commodity identification model, the model extracts a characteristic matrix from the picture through a series of parameters, and the commodity category with the maximum probability corresponding to the characteristic matrix is returned.
5) The commodity picture is collected on the terminal equipment, after a customer selects a commodity, the commodity is placed on an intelligent electronic scale weighing platform, a camera arranged obliquely above the electronic scale weighing platform samples the commodity picture on the electronic scale weighing platform, the electronic scale weighing platform is used as a reference background, the commodity size is identified through calculation of the distance between the commodity and the camera and the distance between the camera and the electronic scale weighing platform, and the difference between a predicted picture result and a real result is reflected by a size loss function value.
6) Inputting the pictures into a commodity identification model, training the model by inquiring a pre-established training data set, matching a feature matrix through picture calculation results, wherein the commodity type with the maximum probability corresponding to the feature matrix is the identified commodity, and acquiring unit prices corresponding to the identified commodity by inquiring a pre-established transaction commodity unit price database; the transaction article unit price database consists of each transaction article and corresponding unit price, and after the article to be transacted is identified, the corresponding unit price can be obtained by inquiring the transaction article unit price database without manual input of an operator; and when the transaction article is updated, correspondingly updating the transaction article unit price database and the image identification template.
7) The commodity identification model returns commodity label printing department, utilizes electronic scale weighing data and trade article unit price database to obtain corresponding unit price and return commodity label printing department, reachs the total price of commodity through the product of unit price and total data, prints commodity total price in commodity label printing department, and staff or buyer paste the commodity label of printing on the commodity wrapping bag, conveniently carry out shopping payment and shopping settlement in the shopping exit.
The intelligent object identifying electronic scales in the fruit area and the vegetable area are independently arranged, so that the mode avoids memory confusion and avoids the situation that the intelligent object identifying electronic scales in the fruit area and the vegetable area simultaneously identify fruit pictures and vegetable pictures.
In the preferred embodiment, under the condition that the varieties cannot be correctly identified, the staff can select the varieties of the commodities on the display screen interface, and the commodity selection identification returns to the commodity label printing place.
The invention also discloses a weighing system of the intelligent object-identifying electronic scale, which comprises a microprocessor for background processing, and a pressure sensor, a camera and a sound device which are respectively connected with the microprocessor;
the pressure sensor is used for acquiring weight data of an article to be traded, and the weight data is amplified and subjected to AD conversion and then transmitted to the microprocessor through a serial port of the single chip microcomputer;
the camera is used for acquiring image data of an article to be traded;
the micro processor is used for receiving data input by the pressure sensor and the camera to carry out intelligent pricing, receiving weight data output by the pressure sensor and image data acquired by the camera by the micro processor to carry out image recognition, calculating the total price of the article to be traded according to the XML unit price database after recognizing the category of the article to be traded, and outputting settlement data through sound equipment after voice synthesis.
The preferred embodiment further comprises an administrator interface, wherein the administrator interface displays the initialization setting information, the transaction article updating information and the transaction article option information, and controls printing to perform corresponding operation after voice recognition.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.
Claims (8)
1. A weighing method of an intelligent object-identifying electronic scale is characterized by comprising the following steps: the specific implementation steps are as follows,
1) collecting pictures of common commodities in a supermarket and preprocessing the pictures;
2) manually marking the category of each commodity picture and making the category into a training data set;
3) constructing a deep convolutional neural network based on increment-v 4;
4) training the model by using a training data set, and storing the trained commodity identification model;
5) acquiring a commodity picture on terminal equipment;
6) inputting the picture into a commodity identification model;
7) the commodity identification model returns to the commodity label printing place.
2. The intelligent electronic scale weighing method of claim 1, characterized in that: in the step 1), the image preprocessing mainly comprises cutting the image to a uniform size, carrying out color acquisition, shape acquisition, mark acquisition and contrast acquisition related processing on the image, neglecting an excessively dark part, and accelerating the operation speed.
3. The intelligent electronic scale weighing method of claim 1, characterized in that: in step 2), the training data set is divided into two parts, according to 8: 2, the data set is divided into a training data set and a testing data set, the training data set is used for training the model, and the testing data set is used for testing the effect of the model and adjusting the optimization method and parameters to prevent the overfitting phenomenon.
4. The intelligent electronic scale weighing method of claim 1, characterized in that: in the step 3), when a neural network model is constructed, the output category number of the model, namely the category number of the commodity, needs to be selected; the loss function value represents the difference between the predicted picture result and the real result, and the lower the loss function value is, the closer the loss function value is to the real result; when a model is constructed, more optimal training parameters including cycle times, learning rate and picture amount of each training need to be selected according to different loss function value results; when the loss function oscillates near the lowest value and does not stably descend any more, the model is shown to be trained to be ended, and the training process is ended in advance to avoid overfitting; the Incep-v 4 adopts an asynchronous SGD (random gradient descent) method, and the learning rate is reduced by 4% for 8 iterations; the final model will evaluate the model performance based on top-1 and top-5 error rates on the test data set.
5. The intelligent electronic scale weighing method of claim 1, characterized in that: in step 4), parameters are selected to determine that a new model is trained when the model is trained, and new commodities are added on the basis of the original model; the commodity pictures collected on the terminal equipment also need to be subjected to image preprocessing; in the identification process, the picture is transmitted into a trained commodity identification model, the model extracts a characteristic matrix from the picture through a series of parameters, and the commodity category with the maximum probability corresponding to the characteristic matrix is returned.
6. The intelligent electronic scale weighing method of claim 1, characterized in that: in step 6), acquiring unit prices corresponding to the identified articles by inquiring a pre-established transaction article unit price database; the trading item unit price database is composed of each trading item and corresponding unit price, and after the item to be traded is identified, the corresponding unit price can be obtained by inquiring the trading item unit price database without manual input of an operator. And when the transaction article is updated, correspondingly updating the transaction article unit price database and the image identification template.
7. The intelligent electronic scale weighing system of any one of claims 1-6, wherein: the system comprises a microprocessor for background processing, and a pressure sensor, a camera and sound equipment which are respectively connected with the microprocessor;
the pressure sensor is used for acquiring weight data of an article to be traded, and the weight data is amplified and subjected to AD conversion and then transmitted to the microprocessor through a serial port of the single chip microcomputer;
the camera is used for acquiring image data of an article to be traded;
the micro processor is used for receiving data input by the pressure sensor and the camera to carry out intelligent pricing, receiving weight data output by the pressure sensor and image data acquired by the camera by the micro processor to carry out image recognition, calculating the total price of the article to be traded according to the XML unit price database after recognizing the category of the article to be traded, and outputting settlement data through sound equipment after voice synthesis.
8. The intelligent electronic scale weighing system of claim 7, wherein: the system also comprises an administrator interface, wherein the administrator interface displays the initialization setting information, the transaction article updating information and the transaction article option information, and controls printing to perform corresponding operation after voice recognition.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010593753.3A CN111814614A (en) | 2020-06-28 | 2020-06-28 | Intelligent object-identifying electronic scale weighing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010593753.3A CN111814614A (en) | 2020-06-28 | 2020-06-28 | Intelligent object-identifying electronic scale weighing method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111814614A true CN111814614A (en) | 2020-10-23 |
Family
ID=72855317
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010593753.3A Pending CN111814614A (en) | 2020-06-28 | 2020-06-28 | Intelligent object-identifying electronic scale weighing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111814614A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112466068A (en) * | 2020-11-26 | 2021-03-09 | 融讯伟业（北京）科技有限公司 | Intelligent weighing device and intelligent weighing method based on computer vision technology |
| CN113177525A (en) * | 2021-05-27 | 2021-07-27 | 杭州有赞科技有限公司 | AI electronic scale system and weighing method |
| CN113569651A (en) * | 2021-06-30 | 2021-10-29 | 青岛海尔科技有限公司 | Resource determination method and device, storage medium and electronic device |
| CN114264360A (en) * | 2021-12-07 | 2022-04-01 | 深圳市博悠半导体科技有限公司 | Object identification method and device based on radar and intelligent electronic scale |
| CN114758194A (en) * | 2022-04-28 | 2022-07-15 | 杭州费尔马科技有限责任公司 | Automatic aquatic product pricing method for intelligent electronic scale |
| WO2023050504A1 (en) * | 2021-09-30 | 2023-04-06 | 厦门顶尖电子有限公司 | Artificial intelligence identification scale management system with multiple weighing platforms |
| CN116403197A (en) * | 2023-03-27 | 2023-07-07 | 广州市智崎衡器有限公司 | Intelligent weighing method and system based on AI image recognition |
| WO2023130429A1 (en) * | 2022-01-10 | 2023-07-13 | 烟台创迹软件有限公司 | Object identification method, object identification apparatus and model learning method |
| WO2023138447A1 (en) * | 2022-01-20 | 2023-07-27 | 索尼半导体解决方案公司 | Ai weighing system, and method for improving precision of ai model by using various types of data sets |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104361698A (en) * | 2014-11-25 | 2015-02-18 | 湖南大学 | Self-service intelligent electronic weighing settlement method and system |
| CN106340137A (en) * | 2016-11-14 | 2017-01-18 | 贵州师范学院 | Automatic weighing machine based on deep learning and program control method thereof |
| CN107767590A (en) * | 2016-08-16 | 2018-03-06 | 深圳仪普生科技有限公司 | Automatic identification commercialization bar code electronic scale and Automatic identification method |
| CN109118200A (en) * | 2018-07-26 | 2019-01-01 | 上海凯景信息技术有限公司 | A kind of commodity identification and cash register system based on image recognition |
| CN109682451A (en) * | 2018-12-17 | 2019-04-26 | 苏州优化智能科技有限公司 | One self-help intelligent identification valuation and label printing system |
| CN110647941A (en) * | 2019-09-25 | 2020-01-03 | 绍兴数鸿科技有限公司 | Vegetable identification method and equipment based on convolutional neural network |
-
2020
- 2020-06-28 CN CN202010593753.3A patent/CN111814614A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104361698A (en) * | 2014-11-25 | 2015-02-18 | 湖南大学 | Self-service intelligent electronic weighing settlement method and system |
| CN107767590A (en) * | 2016-08-16 | 2018-03-06 | 深圳仪普生科技有限公司 | Automatic identification commercialization bar code electronic scale and Automatic identification method |
| CN106340137A (en) * | 2016-11-14 | 2017-01-18 | 贵州师范学院 | Automatic weighing machine based on deep learning and program control method thereof |
| CN109118200A (en) * | 2018-07-26 | 2019-01-01 | 上海凯景信息技术有限公司 | A kind of commodity identification and cash register system based on image recognition |
| CN109682451A (en) * | 2018-12-17 | 2019-04-26 | 苏州优化智能科技有限公司 | One self-help intelligent identification valuation and label printing system |
| CN110647941A (en) * | 2019-09-25 | 2020-01-03 | 绍兴数鸿科技有限公司 | Vegetable identification method and equipment based on convolutional neural network |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112466068A (en) * | 2020-11-26 | 2021-03-09 | 融讯伟业（北京）科技有限公司 | Intelligent weighing device and intelligent weighing method based on computer vision technology |
| CN112466068B (en) * | 2020-11-26 | 2021-07-09 | 融讯伟业（北京）科技有限公司 | Intelligent weighing device and intelligent weighing method based on computer vision technology |
| CN113177525A (en) * | 2021-05-27 | 2021-07-27 | 杭州有赞科技有限公司 | AI electronic scale system and weighing method |
| CN113569651A (en) * | 2021-06-30 | 2021-10-29 | 青岛海尔科技有限公司 | Resource determination method and device, storage medium and electronic device |
| CN113569651B (en) * | 2021-06-30 | 2024-03-22 | 青岛海尔科技有限公司 | Resource determination method and device, storage medium and electronic device |
| WO2023050504A1 (en) * | 2021-09-30 | 2023-04-06 | 厦门顶尖电子有限公司 | Artificial intelligence identification scale management system with multiple weighing platforms |
| CN114264360A (en) * | 2021-12-07 | 2022-04-01 | 深圳市博悠半导体科技有限公司 | Object identification method and device based on radar and intelligent electronic scale |
| WO2023130429A1 (en) * | 2022-01-10 | 2023-07-13 | 烟台创迹软件有限公司 | Object identification method, object identification apparatus and model learning method |
| WO2023138447A1 (en) * | 2022-01-20 | 2023-07-27 | 索尼半导体解决方案公司 | Ai weighing system, and method for improving precision of ai model by using various types of data sets |
| CN114758194A (en) * | 2022-04-28 | 2022-07-15 | 杭州费尔马科技有限责任公司 | Automatic aquatic product pricing method for intelligent electronic scale |
| CN116403197A (en) * | 2023-03-27 | 2023-07-07 | 广州市智崎衡器有限公司 | Intelligent weighing method and system based on AI image recognition |
| CN116403197B (en) * | 2023-03-27 | 2024-01-26 | 广州市智崎衡器有限公司 | Intelligent weighing method and system based on AI image recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111814614A (en) | Intelligent object-identifying electronic scale weighing method and system | |
| JP6709862B6 (en) | Accounting method and equipment by convolutional neural network image recognition technology | |
| CN104361698B (en) | Self-help intelligent electronic-weighing settlement method and system | |
| US20240020672A1 (en) | Intelligent weighing apparatus based on computer vision technology, and intelligent weighing method | |
| CN206019822U (en) | A kind of intelligent electronic-scale based on Internet of Things | |
| CN107767590A (en) | Automatic identification commercialization bar code electronic scale and Automatic identification method | |
| US6363366B1 (en) | Produce identification and pricing system for checkouts | |
| CN109559457A (en) | Cash method and self-service cashier based on neural network recognization commodity | |
| US8286868B2 (en) | Checkout methods and apparatus | |
| CN110836717A (en) | Financial service-oriented intelligent fruit and vegetable identification and pricing system | |
| JP2012256093A (en) | Commodity retrieval device and commodity information processing device | |
| CN111652283A (en) | Vegetable and fruit identification method, settlement equipment and use method | |
| CN111222389A (en) | Method and system for analyzing commodities on commercial and super goods shelf | |
| CN110942293A (en) | Article information processing method, device, storage medium and system | |
| CN115861986B (en) | Non-standard intelligent identification and loss prevention method based on supermarket self-service checkout system | |
| CN110909698A (en) | Electronic scale recognition result output method, system, device and readable storage medium | |
| CN108593075A (en) | A kind of SCM Based Multifunctional electronic scale | |
| CN108645495A (en) | A kind of intelligence can trace electronic scale | |
| WO2021048813A1 (en) | Scale and method for the automatic recognition of a product | |
| CN112116768A (en) | Intelligent commodity identification, classification, metering and pricing system | |
| CN113139768B (en) | Goods shortage monitoring method based on unmanned vending machine | |
| Kaushik et al. | Revamping Supermarkets With AI and RSSi | |
| CN113903127A (en) | Artificial intelligent identification scale management system with multiple weighing platforms | |
| CN110987140A (en) | Commodity weighing auxiliary equipment and weighing equipment | |
| CN111353389A (en) | Intelligent weighing device based on multi-sensor recognition and analysis method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |